> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Data Extraction & Structured Output

> Extract structured data from unstructured text using JSON schemas.

## Best Model for This

| Model           | Why                              | Cost per 1K extractions |
| --------------- | -------------------------------- | ----------------------- |
| `qwen-3-32b`    | Fast, accurate JSON, low cost    | \~\$0.40                |
| `deepseek-v3`   | Best for complex nested schemas  | \~\$0.75                |
| `llama-3.3-70b` | Good balance of speed + accuracy | \~\$1.00                |

Costs assume \~400 tokens input + \~200 tokens output per extraction.

## Quick Start

<CodeGroup>
  ```python Python theme={null}
  import json
  from openai import OpenAI
  from pydantic import BaseModel

  client = OpenAI(
      base_url="https://kymaapi.com/v1",
      api_key="ky-your-api-key"
  )

  class Invoice(BaseModel):
      vendor: str
      amount: float
      currency: str
      date: str
      line_items: list[str]

  SYSTEM = ('Extract invoice data as JSON. Schema: {"vendor": str, "amount": float, '
            '"currency": str, "date": "YYYY-MM-DD", "line_items": [str]}. JSON only.')

  def extract_invoice(text: str) -> Invoice:
      resp = client.chat.completions.create(
          model="qwen-3-32b",
          messages=[{"role": "system", "content": SYSTEM}, {"role": "user", "content": text}],
          response_format={"type": "json_object"},
          temperature=0
      )
      return Invoice(**json.loads(resp.choices[0].message.content))

  raw = "Invoice from Acme Corp, March 15 2025. 10x Widget A @ $5, 2x Widget B @ $12.50. Total $75 USD."
  invoice = extract_invoice(raw)
  print(f"Vendor: {invoice.vendor}, Amount: {invoice.currency}{invoice.amount}")
  ```

  ```javascript JavaScript theme={null}
  import OpenAI from "openai";
  import { z } from "zod";

  const client = new OpenAI({
    baseURL: "https://kymaapi.com/v1",
    apiKey: "ky-your-api-key",
  });

  const InvoiceSchema = z.object({
    vendor: z.string(),
    amount: z.number(),
    currency: z.string(),
    date: z.string(),
    line_items: z.array(z.string()),
  });

  const SYSTEM = 'Extract invoice data as JSON. Schema: {"vendor": string, "amount": number, ' +
                 '"currency": string, "date": "YYYY-MM-DD", "line_items": string[]}. JSON only.';

  async function extractInvoice(text) {
    const resp = await client.chat.completions.create({
      model: "qwen-3-32b",
      messages: [{ role: "system", content: SYSTEM }, { role: "user", content: text }],
      response_format: { type: "json_object" },
      temperature: 0,
    });
    return InvoiceSchema.parse(JSON.parse(resp.choices[0].message.content));
  }

  const raw = "Invoice from Acme Corp, March 15 2025. 10x Widget A @ $5, 2x Widget B @ $12.50. Total $75 USD.";
  const invoice = await extractInvoice(raw);
  console.log(`Vendor: ${invoice.vendor}, Amount: ${invoice.currency}${invoice.amount}`);
  ```
</CodeGroup>

## Tips & Best Practices

* **Always set `temperature=0`** — extraction is deterministic, not creative. Higher temperatures introduce variation in field names and values.
* **Always validate output** — use Pydantic or Zod. Models occasionally miss optional fields or format dates differently.
* **Provide examples in the system prompt** — one example of input + expected output dramatically improves accuracy on complex schemas.
* **Use `response_format: json_object`** — guarantees JSON-parseable output, prevents markdown wrapping or prose before the JSON.

## Cost Estimate

| Volume               | Model         | Monthly cost  |
| -------------------- | ------------- | ------------- |
| 10K extractions/day  | `qwen-3-32b`  | \~\$12/month  |
| 10K extractions/day  | `deepseek-v3` | \~\$22/month  |
| 100K extractions/day | `qwen-3-32b`  | \~\$120/month |

Assumes \~400 tokens input + \~200 tokens output per extraction. Token count scales with document length.

## Next Steps

* [Structured Outputs](/guides/structured-outputs) — enforced JSON schema reference
* [Error Handling](/guides/error-handling) — handle malformed JSON and retries
* [Prompt Caching](/guides/prompt-caching) — cache the system prompt when processing batches